The Highest Ranked StarCraft II BOTS Are INSANE

How to play vs the bots: www.probotsai....
How to watch replays: aiarena.net/wi...
Where to download replays: aiarena.net/re...
Make your own bot: www.versusai.n...
Patreon: / harstem
Daily Stream highlights: / @harstemdaily
My second youtube channel: / @harstemcasts
Twitter: / harstemsc2
Twitch: / harstem
Instagram : / harstemsc
#harstem #SC2 #StarCraft2

[@Tekki_89]

is the deepmind still a thing? i remember them implementing as "alphastar" or like that years ago to get the sense of strats etc. btw im so hyped for the rank roulette coming up, love the series ^^

[@UberKrang]

As far as I know they achieved their goal and therefore the project is completed, and sadly alphastar isn't available :(. Sadly these teams don't have google level resources, alphastar was insane and ended up beating serral and ended up being stronger than anyone in starcraft with a few *.

[@thayerbirch4847]

Deepmind is still a thing, but they stopped developing alphastar about 5 years ago. The project they did after "alphafold" won a nobel prize this year.

[@noobzerg1990]

⁠@@UberKrangThe ai was definitely not the best. It did beat serral 2-0 but serral played poorly. Harstem even beat the bot when it was at its peak. And so did many other pros. It was easy to beat by players in mid gm to top gm I remember it was around 4.8-5.2k or smth like that before they took it down.

[@noaccount4]

Alphastar was an AI trained bot, this series is a bunch of independent programmers making bots for fun. Some use AI, some use a set of pre-programmed rules, lots of very fun bots. My favourite is Ketroc's (anyone who watched LagTV will remember Ketroc was a player infamous for doing mass ravens or planetary fortress rushes). Ketroc's bot will do weird stuff like mass ghosts or ravens, try fill the map with planetaries, and if it gets well-established will begin mule-mining the enemy's mineral patches to deny the enemy minerals. The other one I love is Sharkbot which is also a chatbot :D

[@ChristianSandviknes]

@@noobzerg1990 If I remember correctly (and that's a big if) Serral was playing the initial version of alphastar, while on the ladder it was a scaled-down version - the initial version had no APM cap, while the one on the ladder did, since they wanted to measure intelligence instead of mechanics.

[@Cellus5000]

My guess is the tags are there to timestamp for the bots on small executable strategies. For example you can see the Bane Drop was executed regardless of the state of the game, which makes sense because as a designer you'd need to code the baneling drop separately to anything discreetly necessary to win (injects, making drones, expanding, etc). So if the bane drop is like an executable for Eris, having it say when it starts the executable will make it much easier to debug

[@thijsjong]

For the protoss its the local optimum problem. It is not going to stumble into the solution and reinforce that behavior. Not being able to warp because the ground is blocked should also give the a.i. info to work with. It cannot formulate a constructive response. Hardcode it to scout expansions with an observerbefore the probe goes there and a units to squash that ling. 2 observers covering the same ground does not help either.

[@Leonhart_93]

There is no "reinforcement", this is a hard coded AI, not one that trains itself. The 2nd type is much more advanced and it would require an insane number of games as training data.

[@rykehuss3435]

Just goes to show these bots dont really understand what theyre doing. Its just learned scripts that are constantly running. A total noob could in 5 min of reading about the units realize that oh yeah the only reason I cant build my base here must be because of borrowed unit -> send observer there with a couple of fighting units -> send them to other expansions too

[@thijsjong]

@@Leonhart_93 ok then my criticism makes little sense. A solution can just be coded. I think a hybrid model of a.i. could work. But the machine learning requires to many games as the number of iterations to learn increases exponentially with the number of variables.

[@mh1593]

@@Leonhart_93 there was AlphaStar who learnt from 65,000 baseline games and then thousands of ladder games in 2019. But that's an exception and was a hugely funded specialist project.

[@sashamakeev7547]

Looks like there just was an oversight on building space being blocked by invisible units. Cause you wont get a red restriction building marker, it just will fail at placing building. So there just wasn't a decision to handle burrowed unit put in place in code of the bot. Just needs a check if building had space but failed to be placed. Then send detection and some units.

[@sashamakeev7547]

<a href="#" class="seekto" data-time="602">10:02</a> here you can see that Deimos is actually throttling his commands for some reason. Since there's seem to be no limit to rate of commands that bots can issue i dont really see why this is happening. It is obvious that phoenixes eventually go attack floating queen but with some surprising delay and one by one. Very strange.

[@alexsimkin6414]

It is really interesting to see a bot game. It would be interesting to see how they improve in the future if other games become available.

[@lodthefraud4993]

So happy to see bots again! I love these casts.

[@mh1593]

there are YT channels who just post AI games. They're pretty mad.

[@zealltube]

Would love to see these bots play Alphastar with uncapped apm

[@ddenozor]

I feel like rather than the lack of APM, a lack of decision making is apparent here. But these AI will only get better and better with time.

[@TritonTv69420]

whoa im less than a few mins in and this is crazy with the mineral micro. thanks for the explaining it.

[@albertschmitz7155]

Legitimately, wouldn't a competitive hybrid human/bot competition be fun? Like a player trains with an bot in archon mode or a mod of it, it gets tailored to that players style, and then the player and their bot play together in a tourney.

[@luckygozer]

I think the bots would need way too many matches to ever be reasonable partners to a players style.

[@jedimindtrick3391]

I agree.​@@luckygozer

[@rykehuss3435]

Its odd that with these uncapped APM's terran bots arent dominating. I heard that with infinite apm marine rush would beat everything since marines are extremely strong if you could individually control each of them in a 30 marine blob

[@enlightenerr8342]

2024 and a bot does not get a fourth base because of a burrowed zergling. Furstrating

[@strammerdetlef]

true

[@Gefriertruhe9000]

The big question is, did the bot exploid the other bot, knowing that it would be overwhelmed with the burying?

[@alreadydeadxx2120]

the bots can see the whole map but they need vision to atk command

[@alreadydeadxx2120]

theyre technically cheating

[@SPQR_14]

If that were true there would be no need for the drone scouting for proxies.

[@gewinnste]

Hm, I don't know ... except for the insane micro, this is actually like bronze league heroes. I mean every single strategic decision is terrible. And why can't they detect borrowed lings? Can't they explicitely code that in? Or are they limited to free self-training by the rules?

[@MadoMax92]

Is there a bot to cannon rush me ? for pracitce

[@boreduser12]

Which race is best for bots?

[@ennead322]

I see that with micro protoss is winning most of the time. Here he just lost because of exploits.

[@egebabus3423]

Bot vs bot zerg should be the best? since bots cannot figure out the way to remove those burrowed zerglings. Protoss bot would 100% win without zergling burrow though

[@boreduser12]

Will these bots beat any pro player 100% of the time? Or are we not there yet?

[@victorpoiesz9265]

Depends whether you let them have unlimited APM. They have a huge advantage with the worker speed and blink/burrow micro.

[@orpheus280]

I have no idea how a human beats these bots without handicaps. Being able to control every single unit at once with mathematically perfect micro is practically unbeatable.

[@blacknyellow962]

No the bots aren't there at this point as they're still required to be hard coded to do things, and tend to have trouble adapting when that hard coded thing goes wrong. Like you saw with the protoss bot it got confused (and lost) because it tried to build bases but couldn't due to the burrowed lings.

[@strammerdetlef]

@@orpheus280 lol as u see its far fromp erfect micro

[@martinprince8253]

quickbot

[@TheGrowing]

love da captain the only thing keeping me losing my diamond games while my opponents act like they just won gsl

[@pauledwards2052]

AI battles would be WAY cooler if they were APM limited to a human level.

[@tomasotomato]

on the other hand, watching these units getting microed individually step by step, click by click, is amusing.

[@strammerdetlef]

not at all